From 54377fcab51f6f1f8807827d3751be42279e1a6a Mon Sep 17 00:00:00 2001 From: KaFai Wan Date: Tue, 21 Apr 2026 23:58:02 +0800 Subject: bpf: Reject TCP_NODELAY in bpf-tcp-cc A BPF TCP congestion control program can call bpf_setsockopt() from its callbacks. In current kernels, if it calls bpf_setsockopt(TCP_NODELAY) from cwnd_event_tx_start(), the call can re-enter the TCP transmit path before the outer tcp_transmit_skb() has completed and advanced the send head. This can re-trigger CA_EVENT_TX_START and lead to unbounded recursion: tcp_transmit_skb() -> tcp_event_data_sent() -> tcp_ca_event(sk, CA_EVENT_TX_START) -> cwnd_event_tx_start() -> bpf_setsockopt(TCP_NODELAY) -> tcp_push_pending_frames() -> tcp_write_xmit() -> tcp_transmit_skb() This leads to unbounded recursion and can overflow the kernel stack. Reject TCP_NODELAY with -EOPNOTSUPP for bpf-tcp-cc by introducing a dedicated setsockopt proto for BPF_PROG_TYPE_STRUCT_OPS TCP congestion control programs. To keep it simple, all tcp-cc ops is rejected for TCP_NODELAY. Fixes: 7e41df5dbba2 ("bpf: Add a few optnames to bpf_setsockopt") Suggested-by: Martin KaFai Lau Signed-off-by: KaFai Wan Signed-off-by: Martin KaFai Lau Reviewed-by: Jiayuan Chen Link: https://patch.msgid.link/20260421155804.135786-3-kafai.wan@linux.dev --- include/linux/bpf.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index b4b703c90ca9..01e203964892 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -3725,6 +3725,7 @@ extern const struct bpf_func_proto bpf_for_each_map_elem_proto; extern const struct bpf_func_proto bpf_btf_find_by_name_kind_proto; extern const struct bpf_func_proto bpf_sk_setsockopt_proto; extern const struct bpf_func_proto bpf_sk_getsockopt_proto; +extern const struct bpf_func_proto bpf_sk_setsockopt_nodelay_proto; extern const struct bpf_func_proto bpf_unlocked_sk_setsockopt_proto; extern const struct bpf_func_proto bpf_unlocked_sk_getsockopt_proto; extern const struct bpf_func_proto bpf_find_vma_proto; -- cgit v1.2.3 From 0de4cb473aed57ee4ba7e0551ad27bddc19fc519 Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Tue, 28 Apr 2026 08:10:43 -0700 Subject: workqueue: fix devm_alloc_workqueue() va_list misuse devm_alloc_workqueue() built a va_list and passed it as a single positional argument to the variadic alloc_workqueue() macro: va_start(args, max_active); wq = alloc_workqueue(fmt, flags, max_active, args); va_end(args); C does not allow forwarding a va_list through a ... parameter. alloc_workqueue() expands to alloc_workqueue_noprof(), which runs its own va_start() over its ... params, so the inner vsnprintf(wq->name, sizeof(wq->name), fmt, args) in __alloc_workqueue() received the outer va_list object as the first variadic slot rather than the caller's actual format arguments. Add a new static helper alloc_workqueue_va() that wraps __alloc_workqueue() and runs wq_init_lockdep() on success, and fold both alloc_workqueue_noprof() and devm_alloc_workqueue_noprof() onto it as suggested by Tejun. The wq_init_lockdep() step is required on the devm path too, otherwise __flush_workqueue()'s on-stack COMPLETION_INITIALIZER_ONSTACK_MAP would NULL-deref wq->lockdep_map. No caller changes are required. devm_alloc_ordered_workqueue() is a macro forwarding to devm_alloc_workqueue() and inherits the fix. Two in-tree callers actively trigger the broken path on every probe: drivers/power/supply/mt6370-charger.c:889 drivers/power/supply/max77705_charger.c:649 both of which use devm_alloc_ordered_workqueue(dev, "%s", 0, dev_name(dev)). A standalone reproducer module is available at[1]. Link: https://github.com/leitao/debug/blob/main/workqueue/valist/wq_va_test.c [1] Fixes: 1dfc9d60a69e ("workqueue: devres: Add device-managed allocate workqueue") Signed-off-by: Breno Leitao Signed-off-by: Tejun Heo --- include/linux/workqueue.h | 6 ++++-- kernel/workqueue.c | 28 +++++++++++++++++++--------- 2 files changed, 23 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index ab6cb70ca1a5..6177624539b3 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -534,8 +534,10 @@ alloc_workqueue_noprof(const char *fmt, unsigned int flags, int max_active, ...) * Pointer to the allocated workqueue on success, %NULL on failure. */ __printf(2, 5) struct workqueue_struct * -devm_alloc_workqueue(struct device *dev, const char *fmt, unsigned int flags, - int max_active, ...); +devm_alloc_workqueue_noprof(struct device *dev, const char *fmt, + unsigned int flags, int max_active, ...); +#define devm_alloc_workqueue(...) \ + alloc_hooks(devm_alloc_workqueue_noprof(__VA_ARGS__)) #ifdef CONFIG_LOCKDEP /** diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 5f747f241a5f..24d0265191d4 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -5906,6 +5906,20 @@ err_destroy: return NULL; } +static struct workqueue_struct *alloc_workqueue_va(const char *fmt, + unsigned int flags, + int max_active, + va_list args) +{ + struct workqueue_struct *wq; + + wq = __alloc_workqueue(fmt, flags, max_active, args); + if (wq) + wq_init_lockdep(wq); + + return wq; +} + __printf(1, 4) struct workqueue_struct *alloc_workqueue_noprof(const char *fmt, unsigned int flags, @@ -5915,12 +5929,8 @@ struct workqueue_struct *alloc_workqueue_noprof(const char *fmt, va_list args; va_start(args, max_active); - wq = __alloc_workqueue(fmt, flags, max_active, args); + wq = alloc_workqueue_va(fmt, flags, max_active, args); va_end(args); - if (!wq) - return NULL; - - wq_init_lockdep(wq); return wq; } @@ -5932,15 +5942,15 @@ static void devm_workqueue_release(void *res) } __printf(2, 5) struct workqueue_struct * -devm_alloc_workqueue(struct device *dev, const char *fmt, unsigned int flags, - int max_active, ...) +devm_alloc_workqueue_noprof(struct device *dev, const char *fmt, + unsigned int flags, int max_active, ...) { struct workqueue_struct *wq; va_list args; int ret; va_start(args, max_active); - wq = alloc_workqueue(fmt, flags, max_active, args); + wq = alloc_workqueue_va(fmt, flags, max_active, args); va_end(args); if (!wq) return NULL; @@ -5951,7 +5961,7 @@ devm_alloc_workqueue(struct device *dev, const char *fmt, unsigned int flags, return wq; } -EXPORT_SYMBOL_GPL(devm_alloc_workqueue); +EXPORT_SYMBOL_GPL(devm_alloc_workqueue_noprof); #ifdef CONFIG_LOCKDEP __printf(1, 5) -- cgit v1.2.3 From 6813985ca456d1f5677ad9554f55805cbf27e16f Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Tue, 28 Apr 2026 17:35:18 +0200 Subject: netfilter: x_tables: add .check_hooks to matches and targets Add a new .check_hooks interface for checking if the match/target is used from the validate hook according to its configuration. Move existing conditional hook check based on the match/target configuration from .checkentry to .check_hooks for the following matches/targets: - addrtype - devgroup - physdev - policy - set - TCPMSS - SET This is a preparation patch to fix nft_compat, not functional changes are intended. Based on patch from Florian Westphal. Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/x_tables.h | 8 ++++ net/netfilter/x_tables.c | 79 ++++++++++++++++++++++++++++++++++---- net/netfilter/xt_TCPMSS.c | 33 ++++++++-------- net/netfilter/xt_addrtype.c | 25 +++++++++--- net/netfilter/xt_devgroup.c | 18 ++++++--- net/netfilter/xt_physdev.c | 20 +++++++--- net/netfilter/xt_policy.c | 24 +++++++++--- net/netfilter/xt_set.c | 39 ++++++++++++------- 8 files changed, 187 insertions(+), 59 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h index 77c778d84d4c..a81b46af5118 100644 --- a/include/linux/netfilter/x_tables.h +++ b/include/linux/netfilter/x_tables.h @@ -146,6 +146,9 @@ struct xt_match { /* Called when user tries to insert an entry of this type. */ int (*checkentry)(const struct xt_mtchk_param *); + /* Called to validate hooks based on the match configuration. */ + int (*check_hooks)(const struct xt_mtchk_param *); + /* Called when entry of this type deleted. */ void (*destroy)(const struct xt_mtdtor_param *); #ifdef CONFIG_NETFILTER_XTABLES_COMPAT @@ -187,6 +190,9 @@ struct xt_target { /* Should return 0 on success or an error code otherwise (-Exxxx). */ int (*checkentry)(const struct xt_tgchk_param *); + /* Called to validate hooks based on the target configuration. */ + int (*check_hooks)(const struct xt_tgchk_param *); + /* Called when entry of this type deleted. */ void (*destroy)(const struct xt_tgdtor_param *); #ifdef CONFIG_NETFILTER_XTABLES_COMPAT @@ -279,8 +285,10 @@ bool xt_find_jump_offset(const unsigned int *offsets, int xt_check_proc_name(const char *name, unsigned int size); +int xt_check_hooks_match(struct xt_mtchk_param *par); int xt_check_match(struct xt_mtchk_param *, unsigned int size, u16 proto, bool inv_proto); +int xt_check_hooks_target(struct xt_tgchk_param *par); int xt_check_target(struct xt_tgchk_param *, unsigned int size, u16 proto, bool inv_proto); diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index 9f837fb5ceb4..2c67c2e6b132 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -477,11 +477,9 @@ int xt_check_proc_name(const char *name, unsigned int size) } EXPORT_SYMBOL(xt_check_proc_name); -int xt_check_match(struct xt_mtchk_param *par, - unsigned int size, u16 proto, bool inv_proto) +static int xt_check_match_common(struct xt_mtchk_param *par, + unsigned int size, u16 proto, bool inv_proto) { - int ret; - if (XT_ALIGN(par->match->matchsize) != size && par->match->matchsize != -1) { /* @@ -530,6 +528,14 @@ int xt_check_match(struct xt_mtchk_param *par, par->match->proto); return -EINVAL; } + + return 0; +} + +static int xt_checkentry_match(struct xt_mtchk_param *par) +{ + int ret; + if (par->match->checkentry != NULL) { ret = par->match->checkentry(par); if (ret < 0) @@ -538,8 +544,34 @@ int xt_check_match(struct xt_mtchk_param *par, /* Flag up potential errors. */ return -EIO; } + + return 0; +} + +int xt_check_hooks_match(struct xt_mtchk_param *par) +{ + if (par->match->check_hooks != NULL) + return par->match->check_hooks(par); + return 0; } +EXPORT_SYMBOL_GPL(xt_check_hooks_match); + +int xt_check_match(struct xt_mtchk_param *par, + unsigned int size, u16 proto, bool inv_proto) +{ + int ret; + + ret = xt_check_match_common(par, size, proto, inv_proto); + if (ret < 0) + return ret; + + ret = xt_check_hooks_match(par); + if (ret < 0) + return ret; + + return xt_checkentry_match(par); +} EXPORT_SYMBOL_GPL(xt_check_match); /** xt_check_entry_match - check that matches end before start of target @@ -1012,11 +1044,9 @@ bool xt_find_jump_offset(const unsigned int *offsets, } EXPORT_SYMBOL(xt_find_jump_offset); -int xt_check_target(struct xt_tgchk_param *par, - unsigned int size, u16 proto, bool inv_proto) +static int xt_check_target_common(struct xt_tgchk_param *par, + unsigned int size, u16 proto, bool inv_proto) { - int ret; - if (XT_ALIGN(par->target->targetsize) != size) { pr_err_ratelimited("%s_tables: %s.%u target: invalid size %u (kernel) != (user) %u\n", xt_prefix[par->family], par->target->name, @@ -1061,6 +1091,23 @@ int xt_check_target(struct xt_tgchk_param *par, par->target->proto); return -EINVAL; } + + return 0; +} + +int xt_check_hooks_target(struct xt_tgchk_param *par) +{ + if (par->target->check_hooks != NULL) + return par->target->check_hooks(par); + + return 0; +} +EXPORT_SYMBOL_GPL(xt_check_hooks_target); + +static int xt_checkentry_target(struct xt_tgchk_param *par) +{ + int ret; + if (par->target->checkentry != NULL) { ret = par->target->checkentry(par); if (ret < 0) @@ -1071,6 +1118,22 @@ int xt_check_target(struct xt_tgchk_param *par, } return 0; } + +int xt_check_target(struct xt_tgchk_param *par, + unsigned int size, u16 proto, bool inv_proto) +{ + int ret; + + ret = xt_check_target_common(par, size, proto, inv_proto); + if (ret < 0) + return ret; + + ret = xt_check_hooks_target(par); + if (ret < 0) + return ret; + + return xt_checkentry_target(par); +} EXPORT_SYMBOL_GPL(xt_check_target); /** diff --git a/net/netfilter/xt_TCPMSS.c b/net/netfilter/xt_TCPMSS.c index 116a885adb3c..80e1634bc51f 100644 --- a/net/netfilter/xt_TCPMSS.c +++ b/net/netfilter/xt_TCPMSS.c @@ -247,6 +247,21 @@ tcpmss_tg6(struct sk_buff *skb, const struct xt_action_param *par) } #endif +static int tcpmss_tg4_check_hooks(const struct xt_tgchk_param *par) +{ + const struct xt_tcpmss_info *info = par->targinfo; + + if (info->mss == XT_TCPMSS_CLAMP_PMTU && + (par->hook_mask & ~((1 << NF_INET_FORWARD) | + (1 << NF_INET_LOCAL_OUT) | + (1 << NF_INET_POST_ROUTING))) != 0) { + pr_info_ratelimited("path-MTU clamping only supported in FORWARD, OUTPUT and POSTROUTING hooks\n"); + return -EINVAL; + } + + return 0; +} + /* Must specify -p tcp --syn */ static inline bool find_syn_match(const struct xt_entry_match *m) { @@ -262,17 +277,9 @@ static inline bool find_syn_match(const struct xt_entry_match *m) static int tcpmss_tg4_check(const struct xt_tgchk_param *par) { - const struct xt_tcpmss_info *info = par->targinfo; const struct ipt_entry *e = par->entryinfo; const struct xt_entry_match *ematch; - if (info->mss == XT_TCPMSS_CLAMP_PMTU && - (par->hook_mask & ~((1 << NF_INET_FORWARD) | - (1 << NF_INET_LOCAL_OUT) | - (1 << NF_INET_POST_ROUTING))) != 0) { - pr_info_ratelimited("path-MTU clamping only supported in FORWARD, OUTPUT and POSTROUTING hooks\n"); - return -EINVAL; - } if (par->nft_compat) return 0; @@ -286,17 +293,9 @@ static int tcpmss_tg4_check(const struct xt_tgchk_param *par) #if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) static int tcpmss_tg6_check(const struct xt_tgchk_param *par) { - const struct xt_tcpmss_info *info = par->targinfo; const struct ip6t_entry *e = par->entryinfo; const struct xt_entry_match *ematch; - if (info->mss == XT_TCPMSS_CLAMP_PMTU && - (par->hook_mask & ~((1 << NF_INET_FORWARD) | - (1 << NF_INET_LOCAL_OUT) | - (1 << NF_INET_POST_ROUTING))) != 0) { - pr_info_ratelimited("path-MTU clamping only supported in FORWARD, OUTPUT and POSTROUTING hooks\n"); - return -EINVAL; - } if (par->nft_compat) return 0; @@ -312,6 +311,7 @@ static struct xt_target tcpmss_tg_reg[] __read_mostly = { { .family = NFPROTO_IPV4, .name = "TCPMSS", + .check_hooks = tcpmss_tg4_check_hooks, .checkentry = tcpmss_tg4_check, .target = tcpmss_tg4, .targetsize = sizeof(struct xt_tcpmss_info), @@ -322,6 +322,7 @@ static struct xt_target tcpmss_tg_reg[] __read_mostly = { { .family = NFPROTO_IPV6, .name = "TCPMSS", + .check_hooks = tcpmss_tg4_check_hooks, .checkentry = tcpmss_tg6_check, .target = tcpmss_tg6, .targetsize = sizeof(struct xt_tcpmss_info), diff --git a/net/netfilter/xt_addrtype.c b/net/netfilter/xt_addrtype.c index a77088943107..913dbe3aa5e2 100644 --- a/net/netfilter/xt_addrtype.c +++ b/net/netfilter/xt_addrtype.c @@ -153,14 +153,10 @@ addrtype_mt_v1(const struct sk_buff *skb, struct xt_action_param *par) return ret; } -static int addrtype_mt_checkentry_v1(const struct xt_mtchk_param *par) +static int addrtype_mt_check_hooks(const struct xt_mtchk_param *par) { - const char *errmsg = "both incoming and outgoing interface limitation cannot be selected"; struct xt_addrtype_info_v1 *info = par->matchinfo; - - if (info->flags & XT_ADDRTYPE_LIMIT_IFACE_IN && - info->flags & XT_ADDRTYPE_LIMIT_IFACE_OUT) - goto err; + const char *errmsg; if (par->hook_mask & ((1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_IN)) && @@ -176,6 +172,21 @@ static int addrtype_mt_checkentry_v1(const struct xt_mtchk_param *par) goto err; } + return 0; +err: + pr_info_ratelimited("%s\n", errmsg); + return -EINVAL; +} + +static int addrtype_mt_checkentry_v1(const struct xt_mtchk_param *par) +{ + const char *errmsg = "both incoming and outgoing interface limitation cannot be selected"; + struct xt_addrtype_info_v1 *info = par->matchinfo; + + if (info->flags & XT_ADDRTYPE_LIMIT_IFACE_IN && + info->flags & XT_ADDRTYPE_LIMIT_IFACE_OUT) + goto err; + #if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) if (par->family == NFPROTO_IPV6) { if ((info->source | info->dest) & XT_ADDRTYPE_BLACKHOLE) { @@ -211,6 +222,7 @@ static struct xt_match addrtype_mt_reg[] __read_mostly = { .family = NFPROTO_IPV4, .revision = 1, .match = addrtype_mt_v1, + .check_hooks = addrtype_mt_check_hooks, .checkentry = addrtype_mt_checkentry_v1, .matchsize = sizeof(struct xt_addrtype_info_v1), .me = THIS_MODULE @@ -221,6 +233,7 @@ static struct xt_match addrtype_mt_reg[] __read_mostly = { .family = NFPROTO_IPV6, .revision = 1, .match = addrtype_mt_v1, + .check_hooks = addrtype_mt_check_hooks, .checkentry = addrtype_mt_checkentry_v1, .matchsize = sizeof(struct xt_addrtype_info_v1), .me = THIS_MODULE diff --git a/net/netfilter/xt_devgroup.c b/net/netfilter/xt_devgroup.c index 9520dd00070b..6d1a44ab5eee 100644 --- a/net/netfilter/xt_devgroup.c +++ b/net/netfilter/xt_devgroup.c @@ -33,14 +33,10 @@ static bool devgroup_mt(const struct sk_buff *skb, struct xt_action_param *par) return true; } -static int devgroup_mt_checkentry(const struct xt_mtchk_param *par) +static int devgroup_mt_check_hooks(const struct xt_mtchk_param *par) { const struct xt_devgroup_info *info = par->matchinfo; - if (info->flags & ~(XT_DEVGROUP_MATCH_SRC | XT_DEVGROUP_INVERT_SRC | - XT_DEVGROUP_MATCH_DST | XT_DEVGROUP_INVERT_DST)) - return -EINVAL; - if (info->flags & XT_DEVGROUP_MATCH_SRC && par->hook_mask & ~((1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_IN) | @@ -56,9 +52,21 @@ static int devgroup_mt_checkentry(const struct xt_mtchk_param *par) return 0; } +static int devgroup_mt_checkentry(const struct xt_mtchk_param *par) +{ + const struct xt_devgroup_info *info = par->matchinfo; + + if (info->flags & ~(XT_DEVGROUP_MATCH_SRC | XT_DEVGROUP_INVERT_SRC | + XT_DEVGROUP_MATCH_DST | XT_DEVGROUP_INVERT_DST)) + return -EINVAL; + + return 0; +} + static struct xt_match devgroup_mt_reg __read_mostly = { .name = "devgroup", .match = devgroup_mt, + .check_hooks = devgroup_mt_check_hooks, .checkentry = devgroup_mt_checkentry, .matchsize = sizeof(struct xt_devgroup_info), .family = NFPROTO_UNSPEC, diff --git a/net/netfilter/xt_physdev.c b/net/netfilter/xt_physdev.c index d2b0b52434fa..dd98f758176c 100644 --- a/net/netfilter/xt_physdev.c +++ b/net/netfilter/xt_physdev.c @@ -91,14 +91,10 @@ match_outdev: return (!!ret ^ !(info->invert & XT_PHYSDEV_OP_OUT)); } -static int physdev_mt_check(const struct xt_mtchk_param *par) +static int physdev_mt_check_hooks(const struct xt_mtchk_param *par) { const struct xt_physdev_info *info = par->matchinfo; - static bool brnf_probed __read_mostly; - if (!(info->bitmask & XT_PHYSDEV_OP_MASK) || - info->bitmask & ~XT_PHYSDEV_OP_MASK) - return -EINVAL; if (info->bitmask & (XT_PHYSDEV_OP_OUT | XT_PHYSDEV_OP_ISOUT) && (!(info->bitmask & XT_PHYSDEV_OP_BRIDGED) || info->invert & XT_PHYSDEV_OP_BRIDGED) && @@ -107,6 +103,18 @@ static int physdev_mt_check(const struct xt_mtchk_param *par) return -EINVAL; } + return 0; +} + +static int physdev_mt_check(const struct xt_mtchk_param *par) +{ + const struct xt_physdev_info *info = par->matchinfo; + static bool brnf_probed __read_mostly; + + if (!(info->bitmask & XT_PHYSDEV_OP_MASK) || + info->bitmask & ~XT_PHYSDEV_OP_MASK) + return -EINVAL; + #define X(memb) strnlen(info->memb, sizeof(info->memb)) >= sizeof(info->memb) if (info->bitmask & XT_PHYSDEV_OP_IN) { if (info->physindev[0] == '\0') @@ -141,6 +149,7 @@ static struct xt_match physdev_mt_reg[] __read_mostly = { { .name = "physdev", .family = NFPROTO_IPV4, + .check_hooks = physdev_mt_check_hooks, .checkentry = physdev_mt_check, .match = physdev_mt, .matchsize = sizeof(struct xt_physdev_info), @@ -149,6 +158,7 @@ static struct xt_match physdev_mt_reg[] __read_mostly = { { .name = "physdev", .family = NFPROTO_IPV6, + .check_hooks = physdev_mt_check_hooks, .checkentry = physdev_mt_check, .match = physdev_mt, .matchsize = sizeof(struct xt_physdev_info), diff --git a/net/netfilter/xt_policy.c b/net/netfilter/xt_policy.c index b5fa65558318..ff54e3a8581e 100644 --- a/net/netfilter/xt_policy.c +++ b/net/netfilter/xt_policy.c @@ -126,13 +126,10 @@ policy_mt(const struct sk_buff *skb, struct xt_action_param *par) return ret; } -static int policy_mt_check(const struct xt_mtchk_param *par) +static int policy_mt_check_hooks(const struct xt_mtchk_param *par) { const struct xt_policy_info *info = par->matchinfo; - const char *errmsg = "neither incoming nor outgoing policy selected"; - - if (!(info->flags & (XT_POLICY_MATCH_IN|XT_POLICY_MATCH_OUT))) - goto err; + const char *errmsg; if (par->hook_mask & ((1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_IN)) && info->flags & XT_POLICY_MATCH_OUT) { @@ -144,6 +141,21 @@ static int policy_mt_check(const struct xt_mtchk_param *par) errmsg = "input policy not valid in POSTROUTING and OUTPUT"; goto err; } + + return 0; +err: + pr_info_ratelimited("%s\n", errmsg); + return -EINVAL; +} + +static int policy_mt_check(const struct xt_mtchk_param *par) +{ + const struct xt_policy_info *info = par->matchinfo; + const char *errmsg = "neither incoming nor outgoing policy selected"; + + if (!(info->flags & (XT_POLICY_MATCH_IN|XT_POLICY_MATCH_OUT))) + goto err; + if (info->len > XT_POLICY_MAX_ELEM) { errmsg = "too many policy elements"; goto err; @@ -158,6 +170,7 @@ static struct xt_match policy_mt_reg[] __read_mostly = { { .name = "policy", .family = NFPROTO_IPV4, + .check_hooks = policy_mt_check_hooks, .checkentry = policy_mt_check, .match = policy_mt, .matchsize = sizeof(struct xt_policy_info), @@ -166,6 +179,7 @@ static struct xt_match policy_mt_reg[] __read_mostly = { { .name = "policy", .family = NFPROTO_IPV6, + .check_hooks = policy_mt_check_hooks, .checkentry = policy_mt_check, .match = policy_mt, .matchsize = sizeof(struct xt_policy_info), diff --git a/net/netfilter/xt_set.c b/net/netfilter/xt_set.c index 731bc2cafae4..4ae04bba9358 100644 --- a/net/netfilter/xt_set.c +++ b/net/netfilter/xt_set.c @@ -430,6 +430,29 @@ set_target_v3(struct sk_buff *skb, const struct xt_action_param *par) return XT_CONTINUE; } +static int +set_target_v3_check_hooks(const struct xt_tgchk_param *par) +{ + const struct xt_set_info_target_v3 *info = par->targinfo; + + if (info->map_set.index != IPSET_INVALID_ID) { + if (strncmp(par->table, "mangle", 7)) { + pr_info_ratelimited("--map-set only usable from mangle table\n"); + return -EINVAL; + } + if (((info->flags & IPSET_FLAG_MAP_SKBPRIO) | + (info->flags & IPSET_FLAG_MAP_SKBQUEUE)) && + (par->hook_mask & ~(1 << NF_INET_FORWARD | + 1 << NF_INET_LOCAL_OUT | + 1 << NF_INET_POST_ROUTING))) { + pr_info_ratelimited("mapping of prio or/and queue is allowed only from OUTPUT/FORWARD/POSTROUTING chains\n"); + return -EINVAL; + } + } + + return 0; +} + static int set_target_v3_checkentry(const struct xt_tgchk_param *par) { @@ -459,20 +482,6 @@ set_target_v3_checkentry(const struct xt_tgchk_param *par) } if (info->map_set.index != IPSET_INVALID_ID) { - if (strncmp(par->table, "mangle", 7)) { - pr_info_ratelimited("--map-set only usable from mangle table\n"); - ret = -EINVAL; - goto cleanup_del; - } - if (((info->flags & IPSET_FLAG_MAP_SKBPRIO) | - (info->flags & IPSET_FLAG_MAP_SKBQUEUE)) && - (par->hook_mask & ~(1 << NF_INET_FORWARD | - 1 << NF_INET_LOCAL_OUT | - 1 << NF_INET_POST_ROUTING))) { - pr_info_ratelimited("mapping of prio or/and queue is allowed only from OUTPUT/FORWARD/POSTROUTING chains\n"); - ret = -EINVAL; - goto cleanup_del; - } index = ip_set_nfnl_get_byindex(par->net, info->map_set.index); if (index == IPSET_INVALID_ID) { @@ -672,6 +681,7 @@ static struct xt_target set_targets[] __read_mostly = { .family = NFPROTO_IPV4, .target = set_target_v3, .targetsize = sizeof(struct xt_set_info_target_v3), + .check_hooks = set_target_v3_check_hooks, .checkentry = set_target_v3_checkentry, .destroy = set_target_v3_destroy, .me = THIS_MODULE @@ -682,6 +692,7 @@ static struct xt_target set_targets[] __read_mostly = { .family = NFPROTO_IPV6, .target = set_target_v3, .targetsize = sizeof(struct xt_set_info_target_v3), + .check_hooks = set_target_v3_check_hooks, .checkentry = set_target_v3_checkentry, .destroy = set_target_v3_destroy, .me = THIS_MODULE -- cgit v1.2.3 From e9766e6f7d330dce7530918d8c6e3ec96d6c6e24 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 28 Apr 2026 10:14:41 +0200 Subject: rseq: Protect rseq_reset() against interrupts rseq_reset() uses memset() to clear the tasks rseq data. That's racy against membarrier() and preemption. Guard it with irqsave to cure this. Fixes: faba9d250eae ("rseq: Introduce struct rseq_data") Reported-by: Dmitry Vyukov Signed-off-by: Thomas Gleixner Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Dmitry Vyukov Tested-by: Dmitry Vyukov Link: https://patch.msgid.link/20260428224427.353887714%40kernel.org Cc: stable@vger.kernel.org --- include/linux/rseq.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rseq.h b/include/linux/rseq.h index b9d62fc2140d..f446909551df 100644 --- a/include/linux/rseq.h +++ b/include/linux/rseq.h @@ -119,6 +119,8 @@ static inline void rseq_virt_userspace_exit(void) static inline void rseq_reset(struct task_struct *t) { + /* Protect against preemption and membarrier IPI */ + guard(irqsave)(); memset(&t->rseq, 0, sizeof(t->rseq)); t->rseq.ids.cpu_id = RSEQ_CPU_ID_UNINITIALIZED; } -- cgit v1.2.3 From e768103cfbac30a49860aca08a7710d39dbdd470 Mon Sep 17 00:00:00 2001 From: Stefan Metzmacher Date: Wed, 29 Apr 2026 15:43:36 +0200 Subject: smb: smbdirect: introduce and use include/linux/smbdirect.h This makes it easier to rebuild cifs.ko and ksmbd.ko against a running kernel. Suggested-by: Christoph Hellwig Link: https://lore.kernel.org/linux-cifs/aehrPuY60VMcYGU8@infradead.org/ Cc: Steve French Cc: Tom Talpey Cc: Long Li Cc: Namjae Jeon Cc: Christoph Hellwig Cc: linux-cifs@vger.kernel.org Cc: samba-technical@lists.samba.org Signed-off-by: Stefan Metzmacher Signed-off-by: Steve French --- MAINTAINERS | 1 + fs/smb/client/smbdirect.c | 1 - fs/smb/client/smbdirect.h | 2 +- fs/smb/server/transport_rdma.c | 1 - fs/smb/server/transport_rdma.h | 2 +- fs/smb/smbdirect/internal.h | 3 +- fs/smb/smbdirect/public.h | 146 -------------------------------- fs/smb/smbdirect/smbdirect.h | 52 ------------ include/linux/smbdirect.h | 186 +++++++++++++++++++++++++++++++++++++++++ 9 files changed, 190 insertions(+), 204 deletions(-) delete mode 100644 fs/smb/smbdirect/public.h delete mode 100644 fs/smb/smbdirect/smbdirect.h create mode 100644 include/linux/smbdirect.h (limited to 'include/linux') diff --git a/MAINTAINERS b/MAINTAINERS index 2c67ee25ffe6..060dca38dbf7 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -24650,6 +24650,7 @@ S: Maintained F: fs/smb/client/smbdirect.* F: fs/smb/smbdirect/ F: fs/smb/server/transport_rdma.* +F: include/linux/smbdirect.h SMC91x ETHERNET DRIVER M: Nicolas Pitre diff --git a/fs/smb/client/smbdirect.c b/fs/smb/client/smbdirect.c index b9826185de18..563ef488a225 100644 --- a/fs/smb/client/smbdirect.c +++ b/fs/smb/client/smbdirect.c @@ -9,7 +9,6 @@ #include "cifs_debug.h" #include "cifsproto.h" #include "smb2proto.h" -#include "../smbdirect/public.h" /* Port numbers for SMBD transport */ #define SMB_PORT 445 diff --git a/fs/smb/client/smbdirect.h b/fs/smb/client/smbdirect.h index 287ac849213d..be205ec02077 100644 --- a/fs/smb/client/smbdirect.h +++ b/fs/smb/client/smbdirect.h @@ -12,7 +12,7 @@ #include "cifsglob.h" -#include "../smbdirect/smbdirect.h" +#include extern int rdma_readwrite_threshold; extern int smbd_max_frmr_depth; diff --git a/fs/smb/server/transport_rdma.c b/fs/smb/server/transport_rdma.c index 346c051e31f5..b6d63ff8a8a3 100644 --- a/fs/smb/server/transport_rdma.c +++ b/fs/smb/server/transport_rdma.c @@ -18,7 +18,6 @@ #include "smb_common.h" #include "../common/smb2status.h" #include "transport_rdma.h" -#include "../smbdirect/public.h" #define SMB_DIRECT_PORT_IWARP 5445 diff --git a/fs/smb/server/transport_rdma.h b/fs/smb/server/transport_rdma.h index bde3d88aecc7..8b78917a1795 100644 --- a/fs/smb/server/transport_rdma.h +++ b/fs/smb/server/transport_rdma.h @@ -25,6 +25,6 @@ static inline void init_smbd_max_io_size(unsigned int sz) { } static inline unsigned int get_smbd_max_read_write_size(struct ksmbd_transport *kt) { return 0; } #endif -#include "../smbdirect/smbdirect.h" +#include #endif /* __KSMBD_TRANSPORT_RDMA_H__ */ diff --git a/fs/smb/smbdirect/internal.h b/fs/smb/smbdirect/internal.h index 82529b41708b..e9959e6dc13a 100644 --- a/fs/smb/smbdirect/internal.h +++ b/fs/smb/smbdirect/internal.h @@ -9,9 +9,8 @@ #define DEFAULT_SYMBOL_NAMESPACE "SMBDIRECT" #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt -#include "smbdirect.h" +#include #include "pdu.h" -#include "public.h" #include diff --git a/fs/smb/smbdirect/public.h b/fs/smb/smbdirect/public.h deleted file mode 100644 index d4fb36e65254..000000000000 --- a/fs/smb/smbdirect/public.h +++ /dev/null @@ -1,146 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* - * Copyright (C) 2025, Stefan Metzmacher - */ - -#ifndef __FS_SMB_COMMON_SMBDIRECT_SMBDIRECT_PUBLIC_H__ -#define __FS_SMB_COMMON_SMBDIRECT_SMBDIRECT_PUBLIC_H__ - -struct smbdirect_buffer_descriptor_v1; -struct smbdirect_socket_parameters; - -struct smbdirect_socket; -struct smbdirect_send_batch; -struct smbdirect_mr_io; - -#include - -u8 smbdirect_netdev_rdma_capable_node_type(struct net_device *netdev); - -bool smbdirect_frwr_is_supported(const struct ib_device_attr *attrs); - -int smbdirect_socket_create_kern(struct net *net, struct smbdirect_socket **_sc); - -int smbdirect_socket_create_accepting(struct rdma_cm_id *id, struct smbdirect_socket **_sc); - -int smbdirect_socket_set_initial_parameters(struct smbdirect_socket *sc, - const struct smbdirect_socket_parameters *sp); - -const struct smbdirect_socket_parameters * -smbdirect_socket_get_current_parameters(struct smbdirect_socket *sc); - -int smbdirect_socket_set_kernel_settings(struct smbdirect_socket *sc, - enum ib_poll_context poll_ctx, - gfp_t gfp_mask); - -#define SMBDIRECT_LOG_ERR 0x0 -#define SMBDIRECT_LOG_INFO 0x1 - -#define SMBDIRECT_LOG_OUTGOING 0x1 -#define SMBDIRECT_LOG_INCOMING 0x2 -#define SMBDIRECT_LOG_READ 0x4 -#define SMBDIRECT_LOG_WRITE 0x8 -#define SMBDIRECT_LOG_RDMA_SEND 0x10 -#define SMBDIRECT_LOG_RDMA_RECV 0x20 -#define SMBDIRECT_LOG_KEEP_ALIVE 0x40 -#define SMBDIRECT_LOG_RDMA_EVENT 0x80 -#define SMBDIRECT_LOG_RDMA_MR 0x100 -#define SMBDIRECT_LOG_RDMA_RW 0x200 -#define SMBDIRECT_LOG_NEGOTIATE 0x400 -void smbdirect_socket_set_logging(struct smbdirect_socket *sc, - void *private_ptr, - bool (*needed)(struct smbdirect_socket *sc, - void *private_ptr, - unsigned int lvl, - unsigned int cls), - void (*vaprintf)(struct smbdirect_socket *sc, - const char *func, - unsigned int line, - void *private_ptr, - unsigned int lvl, - unsigned int cls, - struct va_format *vaf)); - -bool smbdirect_connection_is_connected(struct smbdirect_socket *sc); - -int smbdirect_connection_wait_for_connected(struct smbdirect_socket *sc); - -int smbdirect_socket_bind(struct smbdirect_socket *sc, struct sockaddr *addr); - -void smbdirect_socket_shutdown(struct smbdirect_socket *sc); - -void smbdirect_socket_release(struct smbdirect_socket *sc); - -int smbdirect_connection_send_batch_flush(struct smbdirect_socket *sc, - struct smbdirect_send_batch *batch, - bool is_last); - -/* - * This is only temporary and only needed - * as long as the client still requires - * to use smbdirect_connection_send_single_iter() - */ -struct smbdirect_send_batch_storage { - union { - struct list_head __msg_list; - __aligned_u64 __space[5]; - }; -}; - -struct smbdirect_send_batch * -smbdirect_init_send_batch_storage(struct smbdirect_send_batch_storage *storage, - bool need_invalidate_rkey, - unsigned int remote_key); - -int smbdirect_connection_send_single_iter(struct smbdirect_socket *sc, - struct smbdirect_send_batch *batch, - struct iov_iter *iter, - unsigned int flags, - u32 remaining_data_length); - -int smbdirect_connection_send_wait_zero_pending(struct smbdirect_socket *sc); - -int smbdirect_connection_send_iter(struct smbdirect_socket *sc, - struct iov_iter *iter, - unsigned int flags, - bool need_invalidate, - unsigned int remote_key); - -int smbdirect_connection_recvmsg(struct smbdirect_socket *sc, - struct msghdr *msg, - unsigned int flags); - -int smbdirect_connect(struct smbdirect_socket *sc, - const struct sockaddr *dst); - -int smbdirect_connect_sync(struct smbdirect_socket *sc, - const struct sockaddr *dst); - -int smbdirect_socket_listen(struct smbdirect_socket *sc, int backlog); - -struct smbdirect_socket *smbdirect_socket_accept(struct smbdirect_socket *lsc, - long timeo, - struct proto_accept_arg *arg); - -int smbdirect_connection_rdma_xmit(struct smbdirect_socket *sc, - void *buf, size_t buf_len, - struct smbdirect_buffer_descriptor_v1 *desc, - size_t desc_len, - bool is_read); - -struct smbdirect_mr_io * -smbdirect_connection_register_mr_io(struct smbdirect_socket *sc, - struct iov_iter *iter, - bool writing, - bool need_invalidate); - -void smbdirect_mr_io_fill_buffer_descriptor(struct smbdirect_mr_io *mr, - struct smbdirect_buffer_descriptor_v1 *v1); - -void smbdirect_connection_deregister_mr_io(struct smbdirect_mr_io *mr); - -void smbdirect_connection_legacy_debug_proc_show(struct smbdirect_socket *sc, - unsigned int rdma_readwrite_threshold, - struct seq_file *m); - -#endif /* __FS_SMB_COMMON_SMBDIRECT_SMBDIRECT_PUBLIC_H__ */ diff --git a/fs/smb/smbdirect/smbdirect.h b/fs/smb/smbdirect/smbdirect.h deleted file mode 100644 index bbab5f7f7cc9..000000000000 --- a/fs/smb/smbdirect/smbdirect.h +++ /dev/null @@ -1,52 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* - * Copyright (C) 2025 Stefan Metzmacher - */ - -#ifndef __FS_SMB_COMMON_SMBDIRECT_SMBDIRECT_H__ -#define __FS_SMB_COMMON_SMBDIRECT_SMBDIRECT_H__ - -#include - -/* SMB-DIRECT buffer descriptor V1 structure [MS-SMBD] 2.2.3.1 */ -struct smbdirect_buffer_descriptor_v1 { - __le64 offset; - __le32 token; - __le32 length; -} __packed; - -/* - * Connection parameters mostly from [MS-SMBD] 3.1.1.1 - * - * These are setup and negotiated at the beginning of a - * connection and remain constant unless explicitly changed. - * - * Some values are important for the upper layer. - */ -struct smbdirect_socket_parameters { - __u64 flags; -#define SMBDIRECT_FLAG_PORT_RANGE_ONLY_IB ((__u64)0x1) -#define SMBDIRECT_FLAG_PORT_RANGE_ONLY_IW ((__u64)0x2) - __u32 resolve_addr_timeout_msec; - __u32 resolve_route_timeout_msec; - __u32 rdma_connect_timeout_msec; - __u32 negotiate_timeout_msec; - __u16 initiator_depth; /* limited to U8_MAX */ - __u16 responder_resources; /* limited to U8_MAX */ - __u16 recv_credit_max; - __u16 send_credit_target; - __u32 max_send_size; - __u32 max_fragmented_send_size; - __u32 max_recv_size; - __u32 max_fragmented_recv_size; - __u32 max_read_write_size; - __u32 max_frmr_depth; - __u32 keepalive_interval_msec; - __u32 keepalive_timeout_msec; -} __packed; - -#define SMBDIRECT_FLAG_PORT_RANGE_MASK ( \ - SMBDIRECT_FLAG_PORT_RANGE_ONLY_IB | \ - SMBDIRECT_FLAG_PORT_RANGE_ONLY_IW) - -#endif /* __FS_SMB_COMMON_SMBDIRECT_SMBDIRECT_H__ */ diff --git a/include/linux/smbdirect.h b/include/linux/smbdirect.h new file mode 100644 index 000000000000..97f5ba730fa7 --- /dev/null +++ b/include/linux/smbdirect.h @@ -0,0 +1,186 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Copyright (C) 2025, Stefan Metzmacher + */ + +#ifndef __LINUX_SMBDIRECT_H__ +#define __LINUX_SMBDIRECT_H__ + +#include + +/* SMB-DIRECT buffer descriptor V1 structure [MS-SMBD] 2.2.3.1 */ +struct smbdirect_buffer_descriptor_v1 { + __le64 offset; + __le32 token; + __le32 length; +} __packed; + +/* + * Connection parameters mostly from [MS-SMBD] 3.1.1.1 + * + * These are setup and negotiated at the beginning of a + * connection and remain constant unless explicitly changed. + * + * Some values are important for the upper layer. + */ +struct smbdirect_socket_parameters { + __u64 flags; +#define SMBDIRECT_FLAG_PORT_RANGE_ONLY_IB ((__u64)0x1) +#define SMBDIRECT_FLAG_PORT_RANGE_ONLY_IW ((__u64)0x2) + __u32 resolve_addr_timeout_msec; + __u32 resolve_route_timeout_msec; + __u32 rdma_connect_timeout_msec; + __u32 negotiate_timeout_msec; + __u16 initiator_depth; /* limited to U8_MAX */ + __u16 responder_resources; /* limited to U8_MAX */ + __u16 recv_credit_max; + __u16 send_credit_target; + __u32 max_send_size; + __u32 max_fragmented_send_size; + __u32 max_recv_size; + __u32 max_fragmented_recv_size; + __u32 max_read_write_size; + __u32 max_frmr_depth; + __u32 keepalive_interval_msec; + __u32 keepalive_timeout_msec; +} __packed; + +#define SMBDIRECT_FLAG_PORT_RANGE_MASK ( \ + SMBDIRECT_FLAG_PORT_RANGE_ONLY_IB | \ + SMBDIRECT_FLAG_PORT_RANGE_ONLY_IW) + +struct smbdirect_socket; +struct smbdirect_send_batch; +struct smbdirect_mr_io; + +#include + +u8 smbdirect_netdev_rdma_capable_node_type(struct net_device *netdev); + +bool smbdirect_frwr_is_supported(const struct ib_device_attr *attrs); + +int smbdirect_socket_create_kern(struct net *net, struct smbdirect_socket **_sc); + +int smbdirect_socket_create_accepting(struct rdma_cm_id *id, struct smbdirect_socket **_sc); + +int smbdirect_socket_set_initial_parameters(struct smbdirect_socket *sc, + const struct smbdirect_socket_parameters *sp); + +const struct smbdirect_socket_parameters * +smbdirect_socket_get_current_parameters(struct smbdirect_socket *sc); + +int smbdirect_socket_set_kernel_settings(struct smbdirect_socket *sc, + enum ib_poll_context poll_ctx, + gfp_t gfp_mask); + +#define SMBDIRECT_LOG_ERR 0x0 +#define SMBDIRECT_LOG_INFO 0x1 + +#define SMBDIRECT_LOG_OUTGOING 0x1 +#define SMBDIRECT_LOG_INCOMING 0x2 +#define SMBDIRECT_LOG_READ 0x4 +#define SMBDIRECT_LOG_WRITE 0x8 +#define SMBDIRECT_LOG_RDMA_SEND 0x10 +#define SMBDIRECT_LOG_RDMA_RECV 0x20 +#define SMBDIRECT_LOG_KEEP_ALIVE 0x40 +#define SMBDIRECT_LOG_RDMA_EVENT 0x80 +#define SMBDIRECT_LOG_RDMA_MR 0x100 +#define SMBDIRECT_LOG_RDMA_RW 0x200 +#define SMBDIRECT_LOG_NEGOTIATE 0x400 +void smbdirect_socket_set_logging(struct smbdirect_socket *sc, + void *private_ptr, + bool (*needed)(struct smbdirect_socket *sc, + void *private_ptr, + unsigned int lvl, + unsigned int cls), + void (*vaprintf)(struct smbdirect_socket *sc, + const char *func, + unsigned int line, + void *private_ptr, + unsigned int lvl, + unsigned int cls, + struct va_format *vaf)); + +bool smbdirect_connection_is_connected(struct smbdirect_socket *sc); + +int smbdirect_connection_wait_for_connected(struct smbdirect_socket *sc); + +int smbdirect_socket_bind(struct smbdirect_socket *sc, struct sockaddr *addr); + +void smbdirect_socket_shutdown(struct smbdirect_socket *sc); + +void smbdirect_socket_release(struct smbdirect_socket *sc); + +int smbdirect_connection_send_batch_flush(struct smbdirect_socket *sc, + struct smbdirect_send_batch *batch, + bool is_last); + +/* + * This is only temporary and only needed + * as long as the client still requires + * to use smbdirect_connection_send_single_iter() + */ +struct smbdirect_send_batch_storage { + union { + struct list_head __msg_list; + __aligned_u64 __space[5]; + }; +}; + +struct smbdirect_send_batch * +smbdirect_init_send_batch_storage(struct smbdirect_send_batch_storage *storage, + bool need_invalidate_rkey, + unsigned int remote_key); + +int smbdirect_connection_send_single_iter(struct smbdirect_socket *sc, + struct smbdirect_send_batch *batch, + struct iov_iter *iter, + unsigned int flags, + u32 remaining_data_length); + +int smbdirect_connection_send_wait_zero_pending(struct smbdirect_socket *sc); + +int smbdirect_connection_send_iter(struct smbdirect_socket *sc, + struct iov_iter *iter, + unsigned int flags, + bool need_invalidate, + unsigned int remote_key); + +int smbdirect_connection_recvmsg(struct smbdirect_socket *sc, + struct msghdr *msg, + unsigned int flags); + +int smbdirect_connect(struct smbdirect_socket *sc, + const struct sockaddr *dst); + +int smbdirect_connect_sync(struct smbdirect_socket *sc, + const struct sockaddr *dst); + +int smbdirect_socket_listen(struct smbdirect_socket *sc, int backlog); + +struct smbdirect_socket *smbdirect_socket_accept(struct smbdirect_socket *lsc, + long timeo, + struct proto_accept_arg *arg); + +int smbdirect_connection_rdma_xmit(struct smbdirect_socket *sc, + void *buf, size_t buf_len, + struct smbdirect_buffer_descriptor_v1 *desc, + size_t desc_len, + bool is_read); + +struct smbdirect_mr_io * +smbdirect_connection_register_mr_io(struct smbdirect_socket *sc, + struct iov_iter *iter, + bool writing, + bool need_invalidate); + +void smbdirect_mr_io_fill_buffer_descriptor(struct smbdirect_mr_io *mr, + struct smbdirect_buffer_descriptor_v1 *v1); + +void smbdirect_connection_deregister_mr_io(struct smbdirect_mr_io *mr); + +void smbdirect_connection_legacy_debug_proc_show(struct smbdirect_socket *sc, + unsigned int rdma_readwrite_threshold, + struct seq_file *m); + +#endif /* __LINUX_SMBDIRECT_H__ */ -- cgit v1.2.3 From 93618edf753838a727dbff63c7c291dee22d656b Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 1 May 2026 08:31:22 -1000 Subject: cgroup: Defer css percpu_ref kill on rmdir until cgroup is depopulated A chain of commits going back to v7.0 reworked rmdir to satisfy the controller invariant that a subsystem's ->css_offline() must not run while tasks are still doing kernel-side work in the cgroup. [1] d245698d727a ("cgroup: Defer task cgroup unlink until after the task is done switching out") [2] a72f73c4dd9b ("cgroup: Don't expose dead tasks in cgroup") [3] 1b164b876c36 ("cgroup: Wait for dying tasks to leave on rmdir") [4] 4c56a8ac6869 ("cgroup: Fix cgroup_drain_dying() testing the wrong condition") [5] 13e786b64bd3 ("cgroup: Increment nr_dying_subsys_* from rmdir context") [1] moved task cset unlink from do_exit() to finish_task_switch() so a task's cset link drops only after the task has fully stopped scheduling. That made tasks past exit_signals() linger on cset->tasks until their final context switch, which led to a series of problems as what userspace expected to see after rmdir diverged from what the kernel needs to wait for. [2]-[5] tried to bridge that divergence: [2] filtered the exiting tasks from cgroup.procs; [3] had rmdir(2) sleep in TASK_UNINTERRUPTIBLE for them; [4] fixed the wait's condition; [5] made nr_dying_subsys_* visible synchronously. The cgroup_drain_dying() wait in [3] turned out to be a dead end. When the rmdir caller is also the reaper of a zombie that pins a pidns teardown (e.g. host PID 1 systemd reaping orphan pids that were re-parented to it during the same teardown), rmdir blocks in TASK_UNINTERRUPTIBLE waiting for those pids to free, the pids can't free because PID 1 is the reaper and it's stuck in rmdir, and the system A-A deadlocks. No internal lock ordering breaks this; the wait itself is the bug. The css killing side that drove the original reorder, however, can be made cleanly asynchronous: ->css_offline() is already async, run from css_killed_work_fn() driven by percpu_ref_kill_and_confirm(). The fix is to make that chain start only after all tasks have left the cgroup. rmdir's user-visible side then returns as soon as cgroup.procs and friends are empty, while ->css_offline() still runs only after the cgroup is fully drained. Verified by the original reproducer (pidns teardown + zombie reaper, runs under vng) which hangs vanilla and succeeds here, and by per-commit deterministic repros for [2], [3], [4], [5] with a boot parameter that widens the post-exit_signals() window so each state is reliably reachable. Some stress tests on top of that. cgroup_apply_control_disable() has the same shape of pre-existing race: when a controller is disabled via subtree_control, kill_css() ran synchronously while tasks past exit_signals() could still be linked to the cgroup's csets, and ->css_offline() could fire before they drained. This patch preserves the existing synchronous behavior at that call site (kill_css_sync() + kill_css_finish() back-to-back) and a follow-up patch will defer kill_css_finish() there using a per-css trigger. This seems like the right approach and I don't see problems with it. The changes are somewhat invasive but not excessively so, so backporting to -stable should be okay. If something does turn out to be wrong, the fallback is to revert the entire chain ([1]-[5]) and rework in the development branch instead. v2: Pin cgrp across the deferred destroy work with explicit cgroup_get()/cgroup_put() around queue_work() and the work_fn. v1 wasn't actually broken (ordered cgroup_offline_wq + queue_work order in cgroup_task_dead() saved it) but the explicit ref removes the dependency on those non-obvious invariants. Also note the pre-existing cgroup_apply_control_disable() race in the description; a follow-up will defer kill_css_finish() there. Fixes: 1b164b876c36 ("cgroup: Wait for dying tasks to leave on rmdir") Cc: stable@vger.kernel.org # v7.0+ Reported-and-tested-by: Martin Pitt Link: https://lore.kernel.org/all/afHNg2VX2jy9bW7y@piware.de/ Link: https://lore.kernel.org/all/35e0670adb4abeab13da2c321582af9f@kernel.org/ Signed-off-by: Tejun Heo Acked-by: Sebastian Andrzej Siewior --- include/linux/cgroup-defs.h | 4 +- kernel/cgroup/cgroup.c | 250 +++++++++++++++++++++----------------------- 2 files changed, 119 insertions(+), 135 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index f42563739d2e..50a784da7a81 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -611,8 +611,8 @@ struct cgroup { /* used to wait for offlining of csses */ wait_queue_head_t offline_waitq; - /* used by cgroup_rmdir() to wait for dying tasks to leave */ - wait_queue_head_t dying_populated_waitq; + /* defers killing csses after removal until cgroup is depopulated */ + struct work_struct finish_destroy_work; /* used to schedule release agent */ struct work_struct release_agent_work; diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index c928dea9dea6..bd10a7e2f9c5 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -264,10 +264,12 @@ static void cgroup_finalize_control(struct cgroup *cgrp, int ret); static void css_task_iter_skip(struct css_task_iter *it, struct task_struct *task); static int cgroup_destroy_locked(struct cgroup *cgrp); +static void cgroup_finish_destroy(struct cgroup *cgrp); +static void kill_css_sync(struct cgroup_subsys_state *css); +static void kill_css_finish(struct cgroup_subsys_state *css); static struct cgroup_subsys_state *css_create(struct cgroup *cgrp, struct cgroup_subsys *ss); static void css_release(struct percpu_ref *ref); -static void kill_css(struct cgroup_subsys_state *css); static int cgroup_addrm_files(struct cgroup_subsys_state *css, struct cgroup *cgrp, struct cftype cfts[], bool is_add); @@ -797,6 +799,16 @@ static void cgroup_update_populated(struct cgroup *cgrp, bool populated) if (was_populated == cgroup_is_populated(cgrp)) break; + /* + * Subtree just emptied below an offlined cgrp. Fire deferred + * destroy. The transition is one-shot. + */ + if (was_populated && !css_is_online(&cgrp->self)) { + cgroup_get(cgrp); + WARN_ON_ONCE(!queue_work(cgroup_offline_wq, + &cgrp->finish_destroy_work)); + } + cgroup1_check_for_release(cgrp); TRACE_CGROUP_PATH(notify_populated, cgrp, cgroup_is_populated(cgrp)); @@ -2039,6 +2051,16 @@ static int cgroup_reconfigure(struct fs_context *fc) return 0; } +static void cgroup_finish_destroy_work_fn(struct work_struct *work) +{ + struct cgroup *cgrp = container_of(work, struct cgroup, finish_destroy_work); + + cgroup_lock(); + cgroup_finish_destroy(cgrp); + cgroup_unlock(); + cgroup_put(cgrp); +} + static void init_cgroup_housekeeping(struct cgroup *cgrp) { struct cgroup_subsys *ss; @@ -2065,7 +2087,7 @@ static void init_cgroup_housekeeping(struct cgroup *cgrp) #endif init_waitqueue_head(&cgrp->offline_waitq); - init_waitqueue_head(&cgrp->dying_populated_waitq); + INIT_WORK(&cgrp->finish_destroy_work, cgroup_finish_destroy_work_fn); INIT_WORK(&cgrp->release_agent_work, cgroup1_release_agent); } @@ -3375,7 +3397,8 @@ static void cgroup_apply_control_disable(struct cgroup *cgrp) if (css->parent && !(cgroup_ss_mask(dsct) & (1 << ss->id))) { - kill_css(css); + kill_css_sync(css); + kill_css_finish(css); } else if (!css_visible(css)) { css_clear_dir(css); if (ss->css_reset) @@ -5514,7 +5537,7 @@ static struct cftype cgroup_psi_files[] = { * css destruction is four-stage process. * * 1. Destruction starts. Killing of the percpu_ref is initiated. - * Implemented in kill_css(). + * Implemented in kill_css_finish(). * * 2. When the percpu_ref is confirmed to be visible as killed on all CPUs * and thus css_tryget_online() is guaranteed to fail, the css can be @@ -5993,7 +6016,7 @@ out_unlock: /* * This is called when the refcnt of a css is confirmed to be killed. * css_tryget_online() is now guaranteed to fail. Tell the subsystem to - * initiate destruction and put the css ref from kill_css(). + * initiate destruction and put the css ref from kill_css_finish(). */ static void css_killed_work_fn(struct work_struct *work) { @@ -6025,15 +6048,12 @@ static void css_killed_ref_fn(struct percpu_ref *ref) } /** - * kill_css - destroy a css - * @css: css to destroy + * kill_css_sync - synchronous half of css teardown + * @css: css being killed * - * This function initiates destruction of @css by removing cgroup interface - * files and putting its base reference. ->css_offline() will be invoked - * asynchronously once css_tryget_online() is guaranteed to fail and when - * the reference count reaches zero, @css will be released. + * See cgroup_destroy_locked(). */ -static void kill_css(struct cgroup_subsys_state *css) +static void kill_css_sync(struct cgroup_subsys_state *css) { struct cgroup_subsys *ss = css->ss; @@ -6056,24 +6076,6 @@ static void kill_css(struct cgroup_subsys_state *css) */ css_clear_dir(css); - /* - * Killing would put the base ref, but we need to keep it alive - * until after ->css_offline(). - */ - css_get(css); - - /* - * cgroup core guarantees that, by the time ->css_offline() is - * invoked, no new css reference will be given out via - * css_tryget_online(). We can't simply call percpu_ref_kill() and - * proceed to offlining css's because percpu_ref_kill() doesn't - * guarantee that the ref is seen as killed on all CPUs on return. - * - * Use percpu_ref_kill_and_confirm() to get notifications as each - * css is confirmed to be seen as killed on all CPUs. - */ - percpu_ref_kill_and_confirm(&css->refcnt, css_killed_ref_fn); - css->cgroup->nr_dying_subsys[ss->id]++; /* * Parent css and cgroup cannot be freed until after the freeing @@ -6086,44 +6088,88 @@ static void kill_css(struct cgroup_subsys_state *css) } /** - * cgroup_destroy_locked - the first stage of cgroup destruction + * kill_css_finish - deferred half of css teardown + * @css: css being killed + * + * See cgroup_destroy_locked(). + */ +static void kill_css_finish(struct cgroup_subsys_state *css) +{ + lockdep_assert_held(&cgroup_mutex); + + /* + * Skip on re-entry: cgroup_apply_control_disable() may have killed @css + * earlier. cgroup_destroy_locked() can still walk it because + * offline_css() (which NULLs cgrp->subsys[ssid]) runs async. + */ + if (percpu_ref_is_dying(&css->refcnt)) + return; + + /* + * Killing would put the base ref, but we need to keep it alive until + * after ->css_offline(). + */ + css_get(css); + + /* + * cgroup core guarantees that, by the time ->css_offline() is invoked, + * no new css reference will be given out via css_tryget_online(). We + * can't simply call percpu_ref_kill() and proceed to offlining css's + * because percpu_ref_kill() doesn't guarantee that the ref is seen as + * killed on all CPUs on return. + * + * Use percpu_ref_kill_and_confirm() to get notifications as each css is + * confirmed to be seen as killed on all CPUs. + */ + percpu_ref_kill_and_confirm(&css->refcnt, css_killed_ref_fn); +} + +/** + * cgroup_destroy_locked - destroy @cgrp (called on rmdir) * @cgrp: cgroup to be destroyed * - * css's make use of percpu refcnts whose killing latency shouldn't be - * exposed to userland and are RCU protected. Also, cgroup core needs to - * guarantee that css_tryget_online() won't succeed by the time - * ->css_offline() is invoked. To satisfy all the requirements, - * destruction is implemented in the following two steps. - * - * s1. Verify @cgrp can be destroyed and mark it dying. Remove all - * userland visible parts and start killing the percpu refcnts of - * css's. Set up so that the next stage will be kicked off once all - * the percpu refcnts are confirmed to be killed. - * - * s2. Invoke ->css_offline(), mark the cgroup dead and proceed with the - * rest of destruction. Once all cgroup references are gone, the - * cgroup is RCU-freed. - * - * This function implements s1. After this step, @cgrp is gone as far as - * the userland is concerned and a new cgroup with the same name may be - * created. As cgroup doesn't care about the names internally, this - * doesn't cause any problem. + * Tear down @cgrp on behalf of rmdir. Constraints: + * + * - Userspace: rmdir must succeed when cgroup.procs and friends are empty. + * + * - Kernel: subsystem ->css_offline() must not run while any task in @cgrp's + * subtree is still doing kernel work. A task hidden from cgroup.procs (past + * exit_signals() with signal->live cleared) can still schedule, allocate, and + * consume resources until its final context switch. Dying descendants in the + * subtree can host such tasks too. + * + * - Kernel: css_tryget_online() must fail by the time ->css_offline() runs. + * + * The destruction runs in three parts: + * + * - This function: synchronous user-visible state teardown plus kill_css_sync() + * on each subsystem css. + * + * - cgroup_finish_destroy(): kicks the percpu_ref kill via kill_css_finish() on + * each subsystem css. Fires once @cgrp's subtree is fully drained, either + * inline here or from cgroup_update_populated(). + * + * - The percpu_ref kill chain: css_killed_ref_fn -> css_killed_work_fn -> + * ->css_offline() -> release/free. + * + * Return 0 on success, -EBUSY if a userspace-visible task or an online child + * remains. */ static int cgroup_destroy_locked(struct cgroup *cgrp) - __releases(&cgroup_mutex) __acquires(&cgroup_mutex) { struct cgroup *tcgrp, *parent = cgroup_parent(cgrp); struct cgroup_subsys_state *css; struct cgrp_cset_link *link; + struct css_task_iter it; + struct task_struct *task; int ssid, ret; lockdep_assert_held(&cgroup_mutex); - /* - * Only migration can raise populated from zero and we're already - * holding cgroup_mutex. - */ - if (cgroup_is_populated(cgrp)) + css_task_iter_start(&cgrp->self, 0, &it); + task = css_task_iter_next(&it); + css_task_iter_end(&it); + if (task) return -EBUSY; /* @@ -6147,9 +6193,8 @@ static int cgroup_destroy_locked(struct cgroup *cgrp) link->cset->dead = true; spin_unlock_irq(&css_set_lock); - /* initiate massacre of all css's */ for_each_css(css, ssid, cgrp) - kill_css(css); + kill_css_sync(css); /* clear and remove @cgrp dir, @cgrp has an extra ref on its kn */ css_clear_dir(&cgrp->self); @@ -6180,79 +6225,27 @@ static int cgroup_destroy_locked(struct cgroup *cgrp) /* put the base reference */ percpu_ref_kill(&cgrp->self.refcnt); + if (!cgroup_is_populated(cgrp)) + cgroup_finish_destroy(cgrp); + return 0; }; /** - * cgroup_drain_dying - wait for dying tasks to leave before rmdir - * @cgrp: the cgroup being removed - * - * cgroup.procs and cgroup.threads use css_task_iter which filters out - * PF_EXITING tasks so that userspace doesn't see tasks that have already been - * reaped via waitpid(). However, cgroup_has_tasks() - which tests whether the - * cgroup has non-empty css_sets - is only updated when dying tasks pass through - * cgroup_task_dead() in finish_task_switch(). This creates a window where - * cgroup.procs reads empty but cgroup_has_tasks() is still true, making rmdir - * fail with -EBUSY from cgroup_destroy_locked() even though userspace sees no - * tasks. - * - * This function aligns cgroup_has_tasks() with what userspace can observe. If - * cgroup_has_tasks() but the task iterator sees nothing (all remaining tasks are - * PF_EXITING), we wait for cgroup_task_dead() to finish processing them. As the - * window between PF_EXITING and cgroup_task_dead() is short, the wait is brief. + * cgroup_finish_destroy - deferred half of @cgrp destruction + * @cgrp: cgroup whose subtree just became empty * - * This function only concerns itself with this cgroup's own dying tasks. - * Whether the cgroup has children is cgroup_destroy_locked()'s problem. - * - * Each cgroup_task_dead() kicks the waitqueue via cset->cgrp_links, and we - * retry the full check from scratch. - * - * Must be called with cgroup_mutex held. + * See cgroup_destroy_locked() for the rationale. */ -static int cgroup_drain_dying(struct cgroup *cgrp) - __releases(&cgroup_mutex) __acquires(&cgroup_mutex) +static void cgroup_finish_destroy(struct cgroup *cgrp) { - struct css_task_iter it; - struct task_struct *task; - DEFINE_WAIT(wait); + struct cgroup_subsys_state *css; + int ssid; lockdep_assert_held(&cgroup_mutex); -retry: - if (!cgroup_has_tasks(cgrp)) - return 0; - - /* Same iterator as cgroup.threads - if any task is visible, it's busy */ - css_task_iter_start(&cgrp->self, 0, &it); - task = css_task_iter_next(&it); - css_task_iter_end(&it); - - if (task) - return -EBUSY; - /* - * All remaining tasks are PF_EXITING and will pass through - * cgroup_task_dead() shortly. Wait for a kick and retry. - * - * cgroup_has_tasks() can't transition from false to true while we're - * holding cgroup_mutex, but the true to false transition happens - * under css_set_lock (via cgroup_task_dead()). We must retest and - * prepare_to_wait() under css_set_lock. Otherwise, the transition - * can happen between our first test and prepare_to_wait(), and we - * sleep with no one to wake us. - */ - spin_lock_irq(&css_set_lock); - if (!cgroup_has_tasks(cgrp)) { - spin_unlock_irq(&css_set_lock); - return 0; - } - prepare_to_wait(&cgrp->dying_populated_waitq, &wait, - TASK_UNINTERRUPTIBLE); - spin_unlock_irq(&css_set_lock); - mutex_unlock(&cgroup_mutex); - schedule(); - finish_wait(&cgrp->dying_populated_waitq, &wait); - mutex_lock(&cgroup_mutex); - goto retry; + for_each_css(css, ssid, cgrp) + kill_css_finish(css); } int cgroup_rmdir(struct kernfs_node *kn) @@ -6264,12 +6257,9 @@ int cgroup_rmdir(struct kernfs_node *kn) if (!cgrp) return 0; - ret = cgroup_drain_dying(cgrp); - if (!ret) { - ret = cgroup_destroy_locked(cgrp); - if (!ret) - TRACE_CGROUP_PATH(rmdir, cgrp); - } + ret = cgroup_destroy_locked(cgrp); + if (!ret) + TRACE_CGROUP_PATH(rmdir, cgrp); cgroup_kn_unlock(kn); return ret; @@ -7029,7 +7019,6 @@ void cgroup_task_exit(struct task_struct *tsk) static void do_cgroup_task_dead(struct task_struct *tsk) { - struct cgrp_cset_link *link; struct css_set *cset; unsigned long flags; @@ -7043,11 +7032,6 @@ static void do_cgroup_task_dead(struct task_struct *tsk) if (thread_group_leader(tsk) && atomic_read(&tsk->signal->live)) list_add_tail(&tsk->cg_list, &cset->dying_tasks); - /* kick cgroup_drain_dying() waiters, see cgroup_rmdir() */ - list_for_each_entry(link, &cset->cgrp_links, cgrp_link) - if (waitqueue_active(&link->cgrp->dying_populated_waitq)) - wake_up(&link->cgrp->dying_populated_waitq); - if (dl_task(tsk)) dec_dl_tasks_cs(tsk); -- cgit v1.2.3 From 60f21a2649308bbd84919ba6656d5ccd660953cf Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 27 Apr 2026 14:16:34 -1000 Subject: cgroup, sched_ext: Include exiting tasks in cgroup iter a72f73c4dd9b ("cgroup: Don't expose dead tasks in cgroup") made css_task_iter_advance() skip exiting tasks so cgroup.procs stays consistent with waitpid() visibility. Unfortunately, this broke scx_task_iter. scx_task_iter walks either scx_tasks (global) or a cgroup subtree via css_task_iter() and the two modes are expected to cover the same set of tasks. After the above change the cgroup-scoped mode silently skips tasks past exit_signals() that are still on scx_tasks. scx_sub_enable_workfn()'s abort path is one of the symptoms: an exiting SCX_TASK_SUB_INIT task can race past the cgroup iter leaking __scx_init_task() state. Other iterations share the same gap. Add CSS_TASK_ITER_WITH_DEAD to opt out of the skip and use it from scx_task_iter(). Fixes: b0e4c2f8a0f0 ("sched_ext: Implement cgroup subtree iteration for scx_task_iter") Reported-by: Cheng-Yang Chou Signed-off-by: Tejun Heo --- include/linux/cgroup.h | 1 + kernel/cgroup/cgroup.c | 8 +++++--- kernel/sched/ext.c | 6 ++++-- 3 files changed, 10 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index e52160e85af4..f6d037a30fd8 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -53,6 +53,7 @@ struct kernel_clone_args; enum css_task_iter_flags { CSS_TASK_ITER_PROCS = (1U << 0), /* walk only threadgroup leaders */ CSS_TASK_ITER_THREADED = (1U << 1), /* walk all threaded css_sets in the domain */ + CSS_TASK_ITER_WITH_DEAD = (1U << 2), /* include exiting tasks */ CSS_TASK_ITER_SKIPPED = (1U << 16), /* internal flags */ }; diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 1f084ee71443..e51ce4cd3739 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -5059,10 +5059,12 @@ repeat: task = list_entry(it->task_pos, struct task_struct, cg_list); /* - * Hide tasks that are exiting but not yet removed. Keep zombie - * leaders with live threads visible. + * Hide tasks that are exiting but not yet removed by default. Keep + * zombie leaders with live threads visible. Usages that need to walk + * every existing task can opt out via CSS_TASK_ITER_WITH_DEAD. */ - if ((task->flags & PF_EXITING) && !atomic_read(&task->signal->live)) + if (!(it->flags & CSS_TASK_ITER_WITH_DEAD) && + (task->flags & PF_EXITING) && !atomic_read(&task->signal->live)) goto repeat; if (it->flags & CSS_TASK_ITER_PROCS) { diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index 9483be03a4ca..dc5d4787296b 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -766,7 +766,8 @@ static void scx_task_iter_start(struct scx_task_iter *iter, struct cgroup *cgrp) lockdep_assert_held(&cgroup_mutex); iter->cgrp = cgrp; iter->css_pos = css_next_descendant_pre(NULL, &iter->cgrp->self); - css_task_iter_start(iter->css_pos, 0, &iter->css_iter); + css_task_iter_start(iter->css_pos, CSS_TASK_ITER_WITH_DEAD, + &iter->css_iter); return; } #endif @@ -866,7 +867,8 @@ static struct task_struct *scx_task_iter_next(struct scx_task_iter *iter) iter->css_pos = css_next_descendant_pre(iter->css_pos, &iter->cgrp->self); if (iter->css_pos) - css_task_iter_start(iter->css_pos, 0, &iter->css_iter); + css_task_iter_start(iter->css_pos, CSS_TASK_ITER_WITH_DEAD, + &iter->css_iter); } return NULL; } -- cgit v1.2.3 From ff9eda4ea906b1f02fc260ddc42d2d9bd736a49c Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 27 Apr 2026 14:16:35 -1000 Subject: sched_ext: Skip past-sched_ext_dead() tasks in scx_task_iter_next_locked() scx_task_iter's cgroup-scoped mode can return tasks whose sched_ext_dead() has already completed: cgroup_task_dead() removes from cset->tasks after sched_ext_dead() in finish_task_switch() and is irq-work deferred on PREEMPT_RT. The global mode is fine - sched_ext_dead() removes from scx_tasks via list_del_init() first. Callers (sub-sched enable prep/abort/apply, scx_sub_disable(), scx_fail_parent()) assume returned tasks are still on @sch and trip WARN_ON_ONCE() or operate on torn-down state otherwise. Set %SCX_TASK_OFF_TASKS in sched_ext_dead() under @p's rq lock and have scx_task_iter_next_locked() skip flagged tasks under the same lock. Setter and reader serialize on the per-task rq lock - no race. Signed-off-by: Tejun Heo --- include/linux/sched/ext.h | 1 + kernel/sched/ext.c | 33 +++++++++++++++++++++++++-------- 2 files changed, 26 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched/ext.h b/include/linux/sched/ext.h index 1a3af2ea2a79..adb9a4de068a 100644 --- a/include/linux/sched/ext.h +++ b/include/linux/sched/ext.h @@ -101,6 +101,7 @@ enum scx_ent_flags { SCX_TASK_DEQD_FOR_SLEEP = 1 << 3, /* last dequeue was for SLEEP */ SCX_TASK_SUB_INIT = 1 << 4, /* task being initialized for a sub sched */ SCX_TASK_IMMED = 1 << 5, /* task is on local DSQ with %SCX_ENQ_IMMED */ + SCX_TASK_OFF_TASKS = 1 << 6, /* removed from scx_tasks by sched_ext_dead() */ /* * Bits 8 and 9 are used to carry task state: diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index dc5d4787296b..3f0d8aeaed81 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -928,16 +928,27 @@ static struct task_struct *scx_task_iter_next_locked(struct scx_task_iter *iter) * * Test for idle_sched_class as only init_tasks are on it. */ - if (p->sched_class != &idle_sched_class) - break; - } - if (!p) - return NULL; + if (p->sched_class == &idle_sched_class) + continue; - iter->rq = task_rq_lock(p, &iter->rf); - iter->locked_task = p; + iter->rq = task_rq_lock(p, &iter->rf); + iter->locked_task = p; - return p; + /* + * cgroup_task_dead() removes the dead tasks from cset->tasks + * after sched_ext_dead() and cgroup iteration may see tasks + * which already finished sched_ext_dead(). %SCX_TASK_OFF_TASKS + * is set by sched_ext_dead() under @p's rq lock. Test it to + * avoid visiting tasks which are already dead from SCX POV. + */ + if (p->scx.flags & SCX_TASK_OFF_TASKS) { + __scx_task_iter_rq_unlock(iter); + continue; + } + + return p; + } + return NULL; } /** @@ -3850,6 +3861,11 @@ void sched_ext_dead(struct task_struct *p) /* * @p is off scx_tasks and wholly ours. scx_root_enable()'s READY -> * ENABLED transitions can't race us. Disable ops for @p. + * + * %SCX_TASK_OFF_TASKS synchronizes against cgroup task iteration - see + * scx_task_iter_next_locked(). NONE tasks need no marking: cgroup + * iteration is only used from sub-sched paths, which require root + * enabled. Root enable transitions every live task to at least READY. */ if (scx_get_task_state(p) != SCX_TASK_NONE) { struct rq_flags rf; @@ -3857,6 +3873,7 @@ void sched_ext_dead(struct task_struct *p) rq = task_rq_lock(p, &rf); scx_disable_and_exit_task(scx_task_sched(p), p); + p->scx.flags |= SCX_TASK_OFF_TASKS; task_rq_unlock(rq, p, &rf); } } -- cgit v1.2.3 From 8f78b749f3da0f43990490b4c1193b5ede3eec0a Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Thu, 30 Apr 2026 10:44:20 +0300 Subject: sched/isolation: Make HK_TYPE_KTHREAD an alias of HK_TYPE_DOMAIN Since commit 041ee6f3727a ("kthread: Rely on HK_TYPE_DOMAIN for preferred affinity management"), kthreads default to use the HK_TYPE_DOMAIN cpumask. IOW, it is no longer affected by the setting of the nohz_full boot kernel parameter. That means HK_TYPE_KTHREAD should now be an alias of HK_TYPE_DOMAIN instead of HK_TYPE_KERNEL_NOISE to correctly reflect the current kthread behavior. Make the change as HK_TYPE_KTHREAD is still being used in some networking code. Fixes: 041ee6f3727a ("kthread: Rely on HK_TYPE_DOMAIN for preferred affinity management") Signed-off-by: Waiman Long Signed-off-by: Julian Anastasov Signed-off-by: Pablo Neira Ayuso --- include/linux/sched/isolation.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched/isolation.h b/include/linux/sched/isolation.h index dc3975ff1b2e..cf0fd03dd7a2 100644 --- a/include/linux/sched/isolation.h +++ b/include/linux/sched/isolation.h @@ -20,6 +20,11 @@ enum hk_type { HK_TYPE_KERNEL_NOISE, HK_TYPE_MAX, + /* + * HK_TYPE_KTHREAD is now an alias of HK_TYPE_DOMAIN + */ + HK_TYPE_KTHREAD = HK_TYPE_DOMAIN, + /* * The following housekeeping types are only set by the nohz_full * boot commandline option. So they can share the same value. @@ -29,7 +34,6 @@ enum hk_type { HK_TYPE_RCU = HK_TYPE_KERNEL_NOISE, HK_TYPE_MISC = HK_TYPE_KERNEL_NOISE, HK_TYPE_WQ = HK_TYPE_KERNEL_NOISE, - HK_TYPE_KTHREAD = HK_TYPE_KERNEL_NOISE }; #ifdef CONFIG_CPU_ISOLATION -- cgit v1.2.3 From b9eac6a9d93c952c4b7775a24d5c7a1bbf4c3c00 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sat, 25 Apr 2026 00:47:54 +0200 Subject: rseq: Revert to historical performance killing behaviour The recent RSEQ optimization work broke the TCMalloc abuse of the RSEQ ABI as it not longer unconditionally updates the CPU, node, mm_cid fields, which are documented as read only for user space. Due to the observed behavior of the kernel it was possible for TCMalloc to overwrite the cpu_id_start field for their own purposes and rely on the kernel to update it unconditionally after each context switch and before signal delivery. The RSEQ ABI only guarantees that these fields are updated when the data changes, i.e. the task is migrated or the MMCID of the task changes due to switching from or to per CPU ownership mode. The optimization work eliminated the unconditional updates and reduced them to the documented ABI guarantees, which results in a massive performance win for syscall, scheduling heavy work loads, which in turn breaks the TCMalloc expectations. There have been several options discussed to restore the TCMalloc functionality while preserving the optimization benefits. They all end up in a series of hard to maintain workarounds, which in the worst case introduce overhead for everyone, e.g. in the scheduler. The requirements of TCMalloc and the optimization work are diametral and the required work arounds are a maintainence burden. They end up as fragile constructs, which are blocking further optimization work and are pretty much guaranteed to cause more subtle issues down the road. The optimization work heavily depends on the generic entry code, which is not used by all architectures yet. So the rework preserved the original mechanism moslty unmodified to keep the support for architectures, which handle rseq in their own exit to user space loop. That code is currently optimized out by the compiler on architectures which use the generic entry code. This allows to revert back to the original behaviour by replacing the compile time constant conditions with a runtime condition where required, which disables the optimization and the dependend time slice extension feature until the run-time condition can be enabled in the RSEQ registration code on a per task basis again. The following changes are required to restore the original behavior, which makes TCMalloc work again: 1) Replace the compile time constant conditionals with runtime conditionals where appropriate to prevent the compiler from optimizing the legacy mode out 2) Enforce unconditional update of IDs on context switch for the non-optimized v1 mode 3) Enforce update of IDs in the pre signal delivery path for the non-optimized v1 mode 4) Enforce update of IDs in the membarrier(RSEQ) IPI for the non-optimized v1 mode 5) Make time slice and future extensions depend on optimized v2 mode This brings back the full performance problems, but preserves the v2 optimization code and for generic entry code using architectures also the TIF_RSEQ optimization which avoids a full evaluation of the exit to user mode loop in many cases. Fixes: 566d8015f7ee ("rseq: Avoid CPU/MM CID updates when no event pending") Reported-by: Mathias Stearn Signed-off-by: Thomas Gleixner Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Dmitry Vyukov Tested-by: Dmitry Vyukov Closes: https://lore.kernel.org/CAHnCjA25b+nO2n5CeifknSKHssJpPrjnf+dtr7UgzRw4Zgu=oA@mail.gmail.com Link: https://patch.msgid.link/20260428224427.517051752%40kernel.org Cc: stable@vger.kernel.org --- include/linux/rseq.h | 35 ++++++++++++++++++++++++----------- include/linux/rseq_entry.h | 39 +++++++++++++++++++++++++++++---------- include/linux/rseq_types.h | 9 ++++++++- kernel/rseq.c | 40 +++++++++++++++++++++++++++++++++------- kernel/sched/membarrier.c | 11 ++++++++++- 5 files changed, 104 insertions(+), 30 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rseq.h b/include/linux/rseq.h index f446909551df..7ef79b25e714 100644 --- a/include/linux/rseq.h +++ b/include/linux/rseq.h @@ -9,6 +9,11 @@ void __rseq_handle_slowpath(struct pt_regs *regs); +static __always_inline bool rseq_v2(struct task_struct *t) +{ + return IS_ENABLED(CONFIG_GENERIC_IRQ_ENTRY) && likely(t->rseq.event.has_rseq > 1); +} + /* Invoked from resume_user_mode_work() */ static inline void rseq_handle_slowpath(struct pt_regs *regs) { @@ -16,8 +21,7 @@ static inline void rseq_handle_slowpath(struct pt_regs *regs) if (current->rseq.event.slowpath) __rseq_handle_slowpath(regs); } else { - /* '&' is intentional to spare one conditional branch */ - if (current->rseq.event.sched_switch & current->rseq.event.has_rseq) + if (current->rseq.event.sched_switch && current->rseq.event.has_rseq) __rseq_handle_slowpath(regs); } } @@ -30,9 +34,9 @@ void __rseq_signal_deliver(int sig, struct pt_regs *regs); */ static inline void rseq_signal_deliver(struct ksignal *ksig, struct pt_regs *regs) { - if (IS_ENABLED(CONFIG_GENERIC_IRQ_ENTRY)) { - /* '&' is intentional to spare one conditional branch */ - if (current->rseq.event.has_rseq & current->rseq.event.user_irq) + if (rseq_v2(current)) { + /* has_rseq is implied in rseq_v2() */ + if (current->rseq.event.user_irq) __rseq_signal_deliver(ksig->sig, regs); } else { if (current->rseq.event.has_rseq) @@ -50,15 +54,22 @@ static __always_inline void rseq_sched_switch_event(struct task_struct *t) { struct rseq_event *ev = &t->rseq.event; - if (IS_ENABLED(CONFIG_GENERIC_IRQ_ENTRY)) { + /* + * Only apply the user_irq optimization for RSEQ ABI V2 registrations. + * Legacy users like TCMalloc rely on the original ABI V1 behaviour + * which updates IDs on every context swtich. + */ + if (rseq_v2(t)) { /* - * Avoid a boat load of conditionals by using simple logic - * to determine whether NOTIFY_RESUME needs to be raised. + * Avoid a boat load of conditionals by using simple logic to + * determine whether TIF_NOTIFY_RESUME or TIF_RSEQ needs to be + * raised. * - * It's required when the CPU or MM CID has changed or - * the entry was from user space. + * It's required when the CPU or MM CID has changed or the entry + * was via interrupt from user space. ev->has_rseq does not have + * to be evaluated here because rseq_v2() implies has_rseq. */ - bool raise = (ev->user_irq | ev->ids_changed) & ev->has_rseq; + bool raise = ev->user_irq | ev->ids_changed; if (raise) { ev->sched_switch = true; @@ -66,6 +77,7 @@ static __always_inline void rseq_sched_switch_event(struct task_struct *t) } } else { if (ev->has_rseq) { + t->rseq.event.ids_changed = true; t->rseq.event.sched_switch = true; rseq_raise_notify_resume(t); } @@ -161,6 +173,7 @@ static inline unsigned int rseq_alloc_align(void) } #else /* CONFIG_RSEQ */ +static inline bool rseq_v2(struct task_struct *t) { return false; } static inline void rseq_handle_slowpath(struct pt_regs *regs) { } static inline void rseq_signal_deliver(struct ksignal *ksig, struct pt_regs *regs) { } static inline void rseq_sched_switch_event(struct task_struct *t) { } diff --git a/include/linux/rseq_entry.h b/include/linux/rseq_entry.h index f11ebd34f8b9..934db41ec782 100644 --- a/include/linux/rseq_entry.h +++ b/include/linux/rseq_entry.h @@ -111,6 +111,20 @@ static __always_inline void rseq_slice_clear_grant(struct task_struct *t) t->rseq.slice.state.granted = false; } +/* + * Open coded, so it can be invoked within a user access region. + * + * This clears the user space state of the time slice extensions field only when + * the task has registered the optimized RSEQ_ABI V2. Some legacy registrations, + * e.g. TCMalloc, have conflicting non-ABI fields in struct RSEQ, which would be + * overwritten by an unconditional write. + */ +#define rseq_slice_clear_user(rseq, efault) \ +do { \ + if (rseq_slice_extension_enabled()) \ + unsafe_put_user(0U, &rseq->slice_ctrl.all, efault); \ +} while (0) + static __always_inline bool __rseq_grant_slice_extension(bool work_pending) { struct task_struct *curr = current; @@ -230,6 +244,7 @@ static __always_inline bool rseq_slice_extension_enabled(void) { return false; } static __always_inline bool rseq_arm_slice_extension_timer(void) { return false; } static __always_inline void rseq_slice_clear_grant(struct task_struct *t) { } static __always_inline bool rseq_grant_slice_extension(unsigned long ti_work, unsigned long mask) { return false; } +#define rseq_slice_clear_user(rseq, efault) do { } while (0) #endif /* !CONFIG_RSEQ_SLICE_EXTENSION */ bool rseq_debug_update_user_cs(struct task_struct *t, struct pt_regs *regs, unsigned long csaddr); @@ -517,11 +532,9 @@ bool rseq_set_ids_get_csaddr(struct task_struct *t, struct rseq_ids *ids, if (csaddr) unsafe_get_user(*csaddr, &rseq->rseq_cs, efault); - /* Open coded, so it's in the same user access region */ - if (rseq_slice_extension_enabled()) { - /* Unconditionally clear it, no point in conditionals */ - unsafe_put_user(0U, &rseq->slice_ctrl.all, efault); - } + /* RSEQ ABI V2 only operations */ + if (rseq_v2(t)) + rseq_slice_clear_user(rseq, efault); } rseq_slice_clear_grant(t); @@ -612,6 +625,14 @@ static __always_inline bool rseq_exit_user_update(struct pt_regs *regs, struct t * interrupts disabled */ guard(pagefault)(); + /* + * This optimization is only valid when the task registered for the + * optimized RSEQ_ABI_V2 variant. Some legacy users rely on the original + * RSEQ implementation behaviour which unconditionally updated the IDs. + * rseq_sched_switch_event() ensures that legacy registrations always + * have both sched_switch and ids_changed set, which is compatible with + * the historical TIF_NOTIFY_RESUME behaviour. + */ if (likely(!t->rseq.event.ids_changed)) { struct rseq __user *rseq = t->rseq.usrptr; /* @@ -623,11 +644,9 @@ static __always_inline bool rseq_exit_user_update(struct pt_regs *regs, struct t scoped_user_rw_access(rseq, efault) { unsafe_get_user(csaddr, &rseq->rseq_cs, efault); - /* Open coded, so it's in the same user access region */ - if (rseq_slice_extension_enabled()) { - /* Unconditionally clear it, no point in conditionals */ - unsafe_put_user(0U, &rseq->slice_ctrl.all, efault); - } + /* RSEQ ABI V2 only operations */ + if (rseq_v2(t)) + rseq_slice_clear_user(rseq, efault); } rseq_slice_clear_grant(t); diff --git a/include/linux/rseq_types.h b/include/linux/rseq_types.h index 0b42045988db..a469c1870849 100644 --- a/include/linux/rseq_types.h +++ b/include/linux/rseq_types.h @@ -9,6 +9,12 @@ #ifdef CONFIG_RSEQ struct rseq; +/* + * rseq_event::has_rseq contains the ABI version number so preserving it + * in AND operations requires a mask. + */ +#define RSEQ_HAS_RSEQ_VERSION_MASK 0xff + /** * struct rseq_event - Storage for rseq related event management * @all: Compound to initialize and clear the data efficiently @@ -17,7 +23,8 @@ struct rseq; * exit to user * @ids_changed: Indicator that IDs need to be updated * @user_irq: True on interrupt entry from user mode - * @has_rseq: True if the task has a rseq pointer installed + * @has_rseq: Greater than 0 if the task has a rseq pointer installed. + * Contains the RSEQ version number * @error: Compound error code for the slow path to analyze * @fatal: User space data corrupted or invalid * @slowpath: Indicator that slow path processing via TIF_NOTIFY_RESUME diff --git a/kernel/rseq.c b/kernel/rseq.c index 586f58f652c6..aa25753ea135 100644 --- a/kernel/rseq.c +++ b/kernel/rseq.c @@ -253,11 +253,14 @@ efault: static void rseq_slowpath_update_usr(struct pt_regs *regs) { /* - * Preserve rseq state and user_irq state. The generic entry code - * clears user_irq on the way out, the non-generic entry - * architectures are not having user_irq. + * Preserve has_rseq and user_irq state. The generic entry code clears + * user_irq on the way out, the non-generic entry architectures are not + * setting user_irq. */ - const struct rseq_event evt_mask = { .has_rseq = true, .user_irq = true, }; + const struct rseq_event evt_mask = { + .has_rseq = RSEQ_HAS_RSEQ_VERSION_MASK, + .user_irq = true, + }; struct task_struct *t = current; struct rseq_ids ids; u32 node_id; @@ -330,8 +333,9 @@ void __rseq_handle_slowpath(struct pt_regs *regs) void __rseq_signal_deliver(int sig, struct pt_regs *regs) { rseq_stat_inc(rseq_stats.signal); + /* - * Don't update IDs, they are handled on exit to user if + * Don't update IDs yet, they are handled on exit to user if * necessary. The important thing is to abort a critical section of * the interrupted context as after this point the instruction * pointer in @regs points to the signal handler. @@ -344,6 +348,13 @@ void __rseq_signal_deliver(int sig, struct pt_regs *regs) current->rseq.event.error = 0; force_sigsegv(sig); } + + /* + * In legacy mode, force the update of IDs before returning to user + * space to stay compatible. + */ + if (!rseq_v2(current)) + rseq_force_update(); } /* @@ -408,6 +419,7 @@ efault: SYSCALL_DEFINE4(rseq, struct rseq __user *, rseq, u32, rseq_len, int, flags, u32, sig) { u32 rseqfl = 0; + u8 version = 1; if (flags & RSEQ_FLAG_UNREGISTER) { if (flags & ~RSEQ_FLAG_UNREGISTER) @@ -461,7 +473,11 @@ SYSCALL_DEFINE4(rseq, struct rseq __user *, rseq, u32, rseq_len, int, flags, u32 if (!access_ok(rseq, rseq_len)) return -EFAULT; - if (IS_ENABLED(CONFIG_RSEQ_SLICE_EXTENSION)) { + /* + * The version check effectivly disables time slice extensions until the + * RSEQ ABI V2 registration are implemented. + */ + if (IS_ENABLED(CONFIG_RSEQ_SLICE_EXTENSION) && version > 1) { if (rseq_slice_extension_enabled()) { rseqfl |= RSEQ_CS_FLAG_SLICE_EXT_AVAILABLE; if (flags & RSEQ_FLAG_SLICE_EXT_DEFAULT_ON) @@ -484,7 +500,15 @@ SYSCALL_DEFINE4(rseq, struct rseq __user *, rseq, u32, rseq_len, int, flags, u32 unsafe_put_user(RSEQ_CPU_ID_UNINITIALIZED, &rseq->cpu_id, efault); unsafe_put_user(0U, &rseq->node_id, efault); unsafe_put_user(0U, &rseq->mm_cid, efault); - unsafe_put_user(0U, &rseq->slice_ctrl.all, efault); + + /* + * All fields past mm_cid are only valid for non-legacy v2 + * registrations. + */ + if (version > 1) { + if (IS_ENABLED(CONFIG_RSEQ_SLICE_EXTENSION)) + unsafe_put_user(0U, &rseq->slice_ctrl.all, efault); + } } /* @@ -712,6 +736,8 @@ int rseq_slice_extension_prctl(unsigned long arg2, unsigned long arg3) return -ENOTSUPP; if (!current->rseq.usrptr) return -ENXIO; + if (!rseq_v2(current)) + return -ENOTSUPP; /* No change? */ if (enable == !!current->rseq.slice.state.enabled) diff --git a/kernel/sched/membarrier.c b/kernel/sched/membarrier.c index 623445603725..226a6329f3e9 100644 --- a/kernel/sched/membarrier.c +++ b/kernel/sched/membarrier.c @@ -199,7 +199,16 @@ static void ipi_rseq(void *info) * is negligible. */ smp_mb(); - rseq_sched_switch_event(current); + /* + * Legacy mode requires that IDs are written and the critical section is + * evaluated. V2 optimized mode handles the critical section and IDs are + * only updated if they change as a consequence of preemption after + * return from this IPI. + */ + if (rseq_v2(current)) + rseq_sched_switch_event(current); + else + rseq_force_update(); } static void ipi_sync_rq_state(void *info) -- cgit v1.2.3 From 82f572449cfe75f12ea985986da60e11f308f77d Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sun, 26 Apr 2026 16:21:02 +0200 Subject: rseq: Implement read only ABI enforcement for optimized RSEQ V2 mode The optimized RSEQ V2 mode requires that user space adheres to the ABI specification and does not modify the read-only fields cpu_id_start, cpu_id, node_id and mm_cid behind the kernel's back. While the kernel does not rely on these fields, the adherence to this is a fundamental prerequisite to allow multiple entities, e.g. libraries, in an application to utilize the full potential of RSEQ without stepping on each other toes. Validate this adherence on every update of these fields. If the kernel detects that user space modified the fields, the application is force terminated. Fixes: d6200245c75e ("rseq: Allow registering RSEQ with slice extension") Signed-off-by: Thomas Gleixner Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Dmitry Vyukov Tested-by: Dmitry Vyukov Link: https://patch.msgid.link/20260428224427.845230956%40kernel.org Cc: stable@vger.kernel.org --- include/linux/rseq_entry.h | 83 +++++++++++++++++----------------------------- include/linux/rseq_types.h | 4 ++- kernel/rseq.c | 5 ++- 3 files changed, 35 insertions(+), 57 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rseq_entry.h b/include/linux/rseq_entry.h index 934db41ec782..2d0295df5107 100644 --- a/include/linux/rseq_entry.h +++ b/include/linux/rseq_entry.h @@ -248,7 +248,6 @@ static __always_inline bool rseq_grant_slice_extension(unsigned long ti_work, un #endif /* !CONFIG_RSEQ_SLICE_EXTENSION */ bool rseq_debug_update_user_cs(struct task_struct *t, struct pt_regs *regs, unsigned long csaddr); -bool rseq_debug_validate_ids(struct task_struct *t); static __always_inline void rseq_note_user_irq_entry(void) { @@ -368,43 +367,6 @@ efault: return false; } -/* - * On debug kernels validate that user space did not mess with it if the - * debug branch is enabled. - */ -bool rseq_debug_validate_ids(struct task_struct *t) -{ - struct rseq __user *rseq = t->rseq.usrptr; - u32 cpu_id, uval, node_id; - - /* - * On the first exit after registering the rseq region CPU ID is - * RSEQ_CPU_ID_UNINITIALIZED and node_id in user space is 0! - */ - node_id = t->rseq.ids.cpu_id != RSEQ_CPU_ID_UNINITIALIZED ? - cpu_to_node(t->rseq.ids.cpu_id) : 0; - - scoped_user_read_access(rseq, efault) { - unsafe_get_user(cpu_id, &rseq->cpu_id_start, efault); - if (cpu_id != t->rseq.ids.cpu_id) - goto die; - unsafe_get_user(uval, &rseq->cpu_id, efault); - if (uval != cpu_id) - goto die; - unsafe_get_user(uval, &rseq->node_id, efault); - if (uval != node_id) - goto die; - unsafe_get_user(uval, &rseq->mm_cid, efault); - if (uval != t->rseq.ids.mm_cid) - goto die; - } - return true; -die: - t->rseq.event.fatal = true; -efault: - return false; -} - #endif /* RSEQ_BUILD_SLOW_PATH */ /* @@ -514,20 +476,32 @@ efault: * faults in task context are fatal too. */ static rseq_inline -bool rseq_set_ids_get_csaddr(struct task_struct *t, struct rseq_ids *ids, - u32 node_id, u64 *csaddr) +bool rseq_set_ids_get_csaddr(struct task_struct *t, struct rseq_ids *ids, u64 *csaddr) { struct rseq __user *rseq = t->rseq.usrptr; - if (static_branch_unlikely(&rseq_debug_enabled)) { - if (!rseq_debug_validate_ids(t)) - return false; - } - scoped_user_rw_access(rseq, efault) { + /* Validate the R/O fields for debug and optimized mode */ + if (static_branch_unlikely(&rseq_debug_enabled) || rseq_v2(t)) { + u32 cpu_id, uval; + + unsafe_get_user(cpu_id, &rseq->cpu_id_start, efault); + if (cpu_id != t->rseq.ids.cpu_id) + goto die; + unsafe_get_user(uval, &rseq->cpu_id, efault); + if (uval != cpu_id) + goto die; + unsafe_get_user(uval, &rseq->node_id, efault); + if (uval != t->rseq.ids.node_id) + goto die; + unsafe_get_user(uval, &rseq->mm_cid, efault); + if (uval != t->rseq.ids.mm_cid) + goto die; + } + unsafe_put_user(ids->cpu_id, &rseq->cpu_id_start, efault); unsafe_put_user(ids->cpu_id, &rseq->cpu_id, efault); - unsafe_put_user(node_id, &rseq->node_id, efault); + unsafe_put_user(ids->node_id, &rseq->node_id, efault); unsafe_put_user(ids->mm_cid, &rseq->mm_cid, efault); if (csaddr) unsafe_get_user(*csaddr, &rseq->rseq_cs, efault); @@ -539,10 +513,13 @@ bool rseq_set_ids_get_csaddr(struct task_struct *t, struct rseq_ids *ids, rseq_slice_clear_grant(t); /* Cache the new values */ - t->rseq.ids.cpu_cid = ids->cpu_cid; + t->rseq.ids = *ids; rseq_stat_inc(rseq_stats.ids); rseq_trace_update(t, ids); return true; + +die: + t->rseq.event.fatal = true; efault: return false; } @@ -552,11 +529,11 @@ efault: * is in a critical section. */ static rseq_inline bool rseq_update_usr(struct task_struct *t, struct pt_regs *regs, - struct rseq_ids *ids, u32 node_id) + struct rseq_ids *ids) { u64 csaddr; - if (!rseq_set_ids_get_csaddr(t, ids, node_id, &csaddr)) + if (!rseq_set_ids_get_csaddr(t, ids, &csaddr)) return false; /* @@ -659,12 +636,12 @@ static __always_inline bool rseq_exit_user_update(struct pt_regs *regs, struct t } struct rseq_ids ids = { - .cpu_id = task_cpu(t), - .mm_cid = task_mm_cid(t), + .cpu_id = task_cpu(t), + .mm_cid = task_mm_cid(t), + .node_id = cpu_to_node(ids.cpu_id), }; - u32 node_id = cpu_to_node(ids.cpu_id); - return rseq_update_usr(t, regs, &ids, node_id); + return rseq_update_usr(t, regs, &ids); efault: return false; } diff --git a/include/linux/rseq_types.h b/include/linux/rseq_types.h index a469c1870849..85739a63e85e 100644 --- a/include/linux/rseq_types.h +++ b/include/linux/rseq_types.h @@ -66,8 +66,9 @@ struct rseq_event { * compiler emit a single compare on 64-bit * @cpu_id: The CPU ID which was written last to user space * @mm_cid: The MM CID which was written last to user space + * @node_id: The node ID which was written last to user space * - * @cpu_id and @mm_cid are updated when the data is written to user space. + * @cpu_id, @mm_cid and @node_id are updated when the data is written to user space. */ struct rseq_ids { union { @@ -77,6 +78,7 @@ struct rseq_ids { u32 mm_cid; }; }; + u32 node_id; }; /** diff --git a/kernel/rseq.c b/kernel/rseq.c index aa25753ea135..101612027f6a 100644 --- a/kernel/rseq.c +++ b/kernel/rseq.c @@ -263,7 +263,6 @@ static void rseq_slowpath_update_usr(struct pt_regs *regs) }; struct task_struct *t = current; struct rseq_ids ids; - u32 node_id; bool event; if (unlikely(t->flags & PF_EXITING)) @@ -299,9 +298,9 @@ static void rseq_slowpath_update_usr(struct pt_regs *regs) if (!event) return; - node_id = cpu_to_node(ids.cpu_id); + ids.node_id = cpu_to_node(ids.cpu_id); - if (unlikely(!rseq_update_usr(t, regs, &ids, node_id))) { + if (unlikely(!rseq_update_usr(t, regs, &ids))) { /* * Clear the errors just in case this might survive magically, but * leave the rest intact. -- cgit v1.2.3